Creator
DeepSeek
Released
2025-12-01
Intelligence
29.4
Artificial Analysis Index
Coding
37.9
Artificial Analysis Index
In $/1M
$0.00
input tokens
Out $/1M
$0.00
output tokens
Blended $/1M
$0.00
3:1 blended
Speed
0
tokens / sec
Benchmark breakdown
Independent evaluation scores, normalized to 0–100.
GPQA Diamond
87
Humanity’s Last Exam
26
MMLU-Pro
86
SciCode
44
LiveCodeBench
90
MATH-500—
AIME 2025
97
τ²-Bench (agentic)
0
Terminal-Bench Hard
35
IFBench
64